Namhyung Kim [Mon, 9 Nov 2015 05:45:44 +0000 (14:45 +0900)]
perf hists browser: Support folded callchains
The folded callchain mode prints all chains in a single line.
Currently perf report --tui doesn't support folded callchains. Like
flat callchains, only leaf nodes are added to the final rbtree so it
should show entries in parent nodes. To do that, add flat_val list to
struct callchain_node and show them along with the (normal) val list.
Namhyung Kim [Mon, 9 Nov 2015 05:45:43 +0000 (14:45 +0900)]
perf hists browser: Support flat callchains
The flat callchain mode is to print all chains in a single, simple
hierarchy so make it easy to see.
Currently perf report --tui doesn't show flat callchains properly. With
flat callchains, only leaf nodes are added to the final rbtree so it
should show entries in parent nodes. To do that, add parent_val list to
struct callchain_node and show them along with the (normal) val list.
For example, consider following callchains with '-g graph'.
Namhyung Kim [Mon, 9 Nov 2015 05:45:41 +0000 (14:45 +0900)]
perf report: Add callchain value option
Now -g/--call-graph option supports how to display callchain values.
Possible values are 'percent', 'period' and 'count'. The percent is
same as before and it's the default behavior. The period displays the
raw period value rather than the percentage. The count displays the
number of occurrences.
Namhyung Kim [Mon, 9 Nov 2015 05:45:37 +0000 (14:45 +0900)]
perf report: Support folded callchain mode on --stdio
Add new call chain option (-g) 'folded' to print callchains in a line.
The callchains are separated by semicolons, and preceded by (absolute)
percent values and a space.
For example, the following 20 lines can be printed in 3 lines with the
folded output mode:
Masami Hiramatsu [Wed, 18 Nov 2015 06:40:35 +0000 (15:40 +0900)]
perf machine: Fix machine__findnew_module_map to put dso
Fix machine__findnew_module_map to drop the reference to the dso because
it is already referenced by both machine__findnew_module_dso() and
map__new2().
Masami Hiramatsu [Wed, 18 Nov 2015 06:40:31 +0000 (15:40 +0900)]
perf tools: Fix __dsos__addnew to put dso after adding it to the list
__dsos__addnew should drop the constructor reference to dso after adding
it to the list, because __dsos__add() will get a reference that will be
kept while it is in the list.
This fixes DSO leaks when entries are removed to the list and the refcount
never gets to zero.
This means that the dso__load_sym calls map__new2 and maps_insert, both
of them bump the map refcount, but map_groups__exit will drop just one
reference.
Fix it by dropping the refcount after inserting it into kmaps.
Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20151118064026.30709.50038.stgit@localhost.localdomain Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Masami Hiramatsu [Thu, 19 Nov 2015 06:04:53 +0000 (15:04 +0900)]
perf tools: Make perf_exec_path() always return malloc'd string
Since system_path() returns malloc'd string if given path is not an
absolute path, perf_exec_path() sometimes returns a static string and
sometimes returns a malloc'd string depending on the environment
variables or command options.
This may cause a memory leak because the caller can not unconditionally
free the returned string.
This fixes perf_exec_path() and system_path() to always return a
malloc'd string, so the caller can always free it.
Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20151119060453.14210.65666.stgit@localhost.localdomain Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Masami Hiramatsu [Wed, 18 Nov 2015 06:40:24 +0000 (15:40 +0900)]
perf machine: Fix to destroy kernel maps when machine exits
Actually machine__exit forgot to call machine__destroy_kernel_maps.
This fixes some memory leaks on map as below.
Without this fix.
----
./perf probe vfs_read
Added new event:
probe:vfs_read (on vfs_read)
You can now use it in all perf tools, such as:
perf record -e probe:vfs_read -aR sleep 1
REFCNT: BUG: Unreclaimed objects found.
REFCNT: Total 4 objects are not reclaimed.
To see all backtraces, rerun with -v option
----
With this fix.
----
./perf probe vfs_read
Added new event:
probe:vfs_read (on vfs_read)
You can now use it in all perf tools, such as:
perf record -e probe:vfs_read -aR sleep 1
REFCNT: BUG: Unreclaimed objects found.
REFCNT: Total 2 objects are not reclaimed.
To see all backtraces, rerun with -v option
----
Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20151118064024.30709.43577.stgit@localhost.localdomain Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
map__new2() returns map with refcnt = 1, and also map_groups__insert
gets it again in__machine__create_kernel_maps().
machine__destroy_kernel_maps() calls map_groups__remove() to
decrement the refcnt, but before decrement it again (corresponding
to map__new2), it makes vmlinux_maps[type] = NULL. And this may
cause a refcnt leak.
Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20151118064022.30709.3897.stgit@localhost.localdomain Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
This pattern clearly shows that the refcnt of the map is acquired twice
by map__new2 and maps__insert but released onlu once at
map_groups__exit, when we purge its maps rbtree.
Since maps__insert already reference counted the map, we have to drop
the constructor (map__new2) reference count right after inserting it.
These happened in machine__findnew_module_map, as below.
----
# eu-addr2line -e ./perf -f 0x4b8aaf
machine__findnew_module_map inlined at util/machine.c:1046
in machine__create_module
util/machine.c:582
# eu-addr2line -e ./perf -f 0x4b8acb
map_groups__insert inlined at util/machine.c:585
in machine__create_module
util/map.h:208
----
(note that both are at util/machine.c:58X which is
machine__findnew_module_map)
Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20151118064020.30709.40499.stgit@localhost.localdomain Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Wang Nan [Tue, 17 Nov 2015 08:32:50 +0000 (08:32 +0000)]
perf test: Mute test cases error messages if verbose == 0
Sometimes error messages in breaks the pretty output of 'perf test'.
For example:
# mv /lib/modules/4.3.0-rc4+/build/vmlinux{,.bak}
# perf test LLVM BPF
35: Test LLVM searching and compiling :
35.1: Basic BPF llvm compiling test : Ok
35.2: Test kbuild searching : Ok
35.3: Compile source for BPF prologue generation test : Ok
37: Test BPF filter :
37.1: Test basic BPF filtering : Ok
37.2: Test BPF prologue generation :Failed to find the path for kernel: No such file or directory FAILED!
This patch mute test cases thoroughly by redirect their stdout and
stderr to /dev/null when verbose == 0. After applying this patch:
# ./perf test LLVM BPF
35: Test LLVM searching and compiling :
35.1: Basic BPF llvm compiling test : Ok
35.2: Test kbuild searching : Ok
35.3: Compile source for BPF prologue generation test : Ok
37: Test BPF filter :
37.1: Test basic BPF filtering : Ok
37.2: Test BPF prologue generation : FAILED!
# ./perf test -v LLVM BPF
35: Test LLVM searching and compiling :
35.1: Basic BPF llvm compiling test :
--- start ---
test child forked, pid 13183
Kernel build dir is set to /lib/modules/4.3.0-rc4+/build
set env: KBUILD_DIR=/lib/modules/4.3.0-rc4+/build
...
bpf: config 'func=null_lseek file->f_mode offset orig' is ok
Looking at the vmlinux_path (7 entries long)
Failed to find the path for kernel: No such file or directory
bpf_probe: failed to convert perf probe eventsFailed to add events selected by BPF
test child finished with -1
---- end ----
Test BPF filter subtest 1: FAILED!
Signed-off-by: Wang Nan <wangnan0@huawei.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1447749170-175898-6-git-send-email-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Wang Nan [Tue, 17 Nov 2015 08:32:49 +0000 (08:32 +0000)]
perf test: Print result for each BPF subtest
This patch prints each sub-tests results for BPF testcases.
Before:
# ./perf test BPF
37: Test BPF filter : Ok
After:
# ./perf test BPF
37: Test BPF filter :
37.1: Test basic BPF filtering : Ok
37.2: Test BPF prologue generation : Ok
When a failure happens:
# cat ~/.perfconfig
[llvm]
clang-path = "/bin/false"
# ./perf test BPF
37: Test BPF filter :
37.1: Test basic BPF filtering : Skip
37.2: Test BPF prologue generation : Skip
Suggested-and-Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Wang Nan <wangnan0@huawei.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1447749170-175898-5-git-send-email-wangnan0@huawei.com
[ Fixed up not to use .func in an anonymous union ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Wang Nan [Tue, 17 Nov 2015 08:32:48 +0000 (08:32 +0000)]
perf test: Print result for each LLVM subtest
Currently 'perf test llvm' and 'perf test BPF' have multiple sub-tests,
but the result is provided in only one line:
# perf test LLVM
35: Test LLVM searching and compiling : Ok
This patch introduces sub-tests support, allowing 'perf test' to report
result for each sub-tests:
# perf test LLVM
35: Test LLVM searching and compiling :
35.1: Basic BPF llvm compiling test : Ok
35.2: Test kbuild searching : Ok
35.3: Compile source for BPF prologue generation test : Ok
When a failure happens:
# cat ~/.perfconfig
[llvm]
clang-path = "/bin/false"
# perf test LLVM
35: Test LLVM searching and compiling :
35.1: Basic BPF llvm compiling test : FAILED!
35.2: Test kbuild searching : Skip
35.3: Compile source for BPF prologue generation test : Skip
And:
# rm ~/.perfconfig
# ./perf test LLVM
35: Test LLVM searching and compiling :
35.1: Basic BPF llvm compiling test : Skip
35.2: Test kbuild searching : Skip
35.3: Compile source for BPF prologue generation test : Skip
Skip by user:
# ./perf test -s 1,`seq -s , 3 42`
1: vmlinux symtab matches kallsyms : Skip (user override)
2: detect openat syscall event : Ok
...
35: Test LLVM searching and compiling : Skip (user override)
...
Suggested-and-Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Wang Nan <wangnan0@huawei.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1447749170-175898-4-git-send-email-wangnan0@huawei.com
[ Changed so that func is not on an anonymous union ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
perf tests: Pass the subtest index to each test routine
Some tests have sub-tests we want to run, so allow passing this.
Wang tried to avoid having to touch all tests, but then, having the
test.func in an anonymous union makes the build fail on older compilers,
like the one in RHEL6, where:
test a = {
.func = foo,
};
fails.
To fix it leave the func pointer in the main structure and pass the subtest
index to all tests, end result function is the same, but we have just one
function pointer, not two, with and without the subtest index as an argument.
Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-5genj0ficwdmelpoqlds0u4y@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Wang Nan [Tue, 17 Nov 2015 08:32:47 +0000 (08:32 +0000)]
perf bpf: Use same BPF program if arguments are identical
This patch allows creating only one BPF program for different
'probe_trace_event'(tev) entries generated by one
'perf_probe_event'(pev) if their prologues are identical.
This is done by comparing the argument list of different tev instances,
and the maps type of prologue and tev using a mapping array. This patch
utilizes qsort to sort the tevs. After sorting, tevs with identical
argument lists will be grouped together.
Wang Nan [Tue, 17 Nov 2015 08:32:46 +0000 (08:32 +0000)]
perf test: Fix 'perf test BPF' when it fails to find a suitable vmlinux
Two bugs in 'perf test BPF' are found when testing BPF prologue without
vmlinux:
# mv /lib/modules/4.3.0-rc4+/build/vmlinux{,.bak}
# ./perf test BPF
37: Test BPF filter :Failed to find the path for kernel: No such file or directory
Ok
Test BPF should fail in this case.
After this patch:
# ./perf test BPF
37: Test BPF filter :Failed to find the path for kernel: No such file or directory
FAILED!
# mv /lib/modules/4.3.0-rc4+/build/vmlinux{.bak,}
# ./perf test BPF
37: Test BPF filter : Ok
Signed-off-by: Wang Nan <wangnan0@huawei.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1447749170-175898-2-git-send-email-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Wang Nan [Mon, 16 Nov 2015 12:10:14 +0000 (12:10 +0000)]
perf test: Test the BPF prologue adding infrastructure
This patch introduces a new BPF script to test the BPF prologue adding
routines. The new script probes at null_lseek, which is the function pointer
used when we try to lseek on '/dev/null'.
The null_lseek function is chosen because it is used by function pointers, so
we don't need to consider inlining and LTO.
By extracting file->f_mode, bpf-script-test-prologue.c should know whether the
file is writable or readonly. According to llseek_loop() and
bpf-script-test-prologue.c, one fourth of total lseeks should be collected.
Committer note:
Testing it:
# perf test -v BPF
<SNIP>
Kernel build dir is set to /lib/modules/4.3.0+/build
set env: KBUILD_DIR=/lib/modules/4.3.0+/build
unset env: KBUILD_OPTS
include option is set to -nostdinc -isystem /usr/lib/gcc/x86_64-redhat-linux/4.9.2/include -I/home/git/linux/arch/x86/include -Iarch/x86/include/generated/uapi -Iarch/x86/include/generated -I/home/git/linux/include -Iinclude -I/home/git/linux/arch/x86/include/uapi -Iarch/x86/include/generated/uapi -I/home/git/linux/include/uapi -Iinclude/generated/uapi -include /home/git/linux/include/linux/kconfig.h
set env: NR_CPUS=4
set env: LINUX_VERSION_CODE=0x40300
set env: CLANG_EXEC=/usr/libexec/icecc/bin/clang
set env: CLANG_OPTIONS=-xc
set env: KERNEL_INC_OPTIONS= -nostdinc -isystem /usr/lib/gcc/x86_64-redhat-linux/4.9.2/include -I/home/git/linux/arch/x86/include -Iarch/x86/include/generated/uapi -Iarch/x86/include/generated -I/home/git/linux/include -Iinclude -I/home/git/linux/arch/x86/include/uapi -Iarch/x86/include/generated/uapi -I/home/git/linux/include/uapi -Iinclude/generated/uapi -include /home/git/linux/include/linux/kconfig.h
set env: WORKING_DIR=/lib/modules/4.3.0+/build
set env: CLANG_SOURCE=-
llvm compiling command template: echo '/*
* bpf-script-test-prologue.c
* Test BPF prologue
*/
#ifndef LINUX_VERSION_CODE
# error Need LINUX_VERSION_CODE
# error Example: for 4.2 kernel, put 'clang-opt="-DLINUX_VERSION_CODE=0x40200" into llvm section of ~/.perfconfig'
#endif
#define SEC(NAME) __attribute__((section(NAME), used))
SEC("func=null_lseek file->f_mode offset orig")
int bpf_func__null_lseek(void *ctx, int err, unsigned long f_mode,
unsigned long offset, unsigned long orig)
{
if (err)
return 0;
if (f_mode & FMODE_WRITE)
return 0;
if (offset & 1)
return 0;
if (orig == SEEK_CUR)
return 0;
return 1;
}
char _license[] SEC("license") = "GPL";
int _version SEC("version") = LINUX_VERSION_CODE;
' | $CLANG_EXEC -D__KERNEL__ -D__NR_CPUS__=$NR_CPUS -DLINUX_VERSION_CODE=$LINUX_VERSION_CODE $CLANG_OPTIONS $KERNEL_INC_OPTIONS -Wno-unused-value -Wno-pointer-sign -working-directory $WORKING_DIR -c "$CLANG_SOURCE" -target bpf -O2 -o -
libbpf: loading object '[bpf_prologue_test]' from buffer
libbpf: section .strtab, size 135, link 0, flags 0, type=3
libbpf: section .text, size 0, link 0, flags 6, type=1
libbpf: section .data, size 0, link 0, flags 3, type=1
libbpf: section .bss, size 0, link 0, flags 3, type=8
libbpf: section func=null_lseek file->f_mode offset orig, size 112, link 0, flags 6, type=1
libbpf: found program func=null_lseek file->f_mode offset orig
libbpf: section license, size 4, link 0, flags 3, type=1
libbpf: license of [bpf_prologue_test] is GPL
libbpf: section version, size 4, link 0, flags 3, type=1
libbpf: kernel version of [bpf_prologue_test] is 40300
libbpf: section .symtab, size 168, link 1, flags 0, type=2
bpf: config program 'func=null_lseek file->f_mode offset orig'
symbol:null_lseek file:(null) line:0 offset:0 return:0 lazy:(null)
parsing arg: file->f_mode into file, f_mode(1)
parsing arg: offset into offset
parsing arg: orig into orig
bpf: config 'func=null_lseek file->f_mode offset orig' is ok
Looking at the vmlinux_path (7 entries long)
Using /lib/modules/4.3.0+/build/vmlinux for symbols
Open Debuginfo file: /lib/modules/4.3.0+/build/vmlinux
Try to find probe point from debuginfo.
Matched function: null_lseek
Probe point found: null_lseek+0
Searching 'file' variable in context.
Converting variable file into trace event.
converting f_mode in file
f_mode type is unsigned int.
Searching 'offset' variable in context.
Converting variable offset into trace event.
offset type is long long int.
Searching 'orig' variable in context.
Converting variable orig into trace event.
orig type is int.
Found 1 probe_trace_events.
Opening /sys/kernel/debug/tracing//kprobe_events write=1
Writing event: p:perf_bpf_probe/func _text+4840528 f_mode=+68(%di):u32 offset=%si:s64 orig=%dx:s32
libbpf: don't need create maps for [bpf_prologue_test]
prologue: pass validation
prologue: slow path
prologue: fetch arg 0, base reg is %di
prologue: arg 0: offset 68
prologue: fetch arg 1, base reg is %si
prologue: fetch arg 2, base reg is %dx
add bpf event perf_bpf_probe:func and attach bpf program 3
adding perf_bpf_probe:func
adding perf_bpf_probe:func to 0x51672c0
mmap size 1052672B
Opening /sys/kernel/debug/tracing//kprobe_events write=1
Opening /sys/kernel/debug/tracing//uprobe_events write=1
Parsing probe_events: p:perf_bpf_probe/func _text+4840528 f_mode=+68(%di):u32 offset=%si:s64 orig=%dx:s32
Group:perf_bpf_probe Event:func probe:p
Writing event: -:perf_bpf_probe/func
test child finished with 0
---- end ----
Test BPF filter: Ok
#
Signed-off-by: Wang Nan <wangnan0@huawei.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1447675815-166222-13-git-send-email-wangnan0@huawei.com
[ Added tools/perf/tests/llvm-src-prologue.c to .gitignore ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Wang Nan [Mon, 16 Nov 2015 12:10:13 +0000 (12:10 +0000)]
perf bpf: Generate prologue for BPF programs
This patch generates a prologue for each 'struct probe_trace_event' for
fetching arguments for BPF programs.
After bpf__probe(), iterate over each program to check whether prologues are
required. If none of the 'struct perf_probe_event' programs will attach to have
at least one argument, simply skip preprocessor hooking. For those who a
prologue is required, call bpf__gen_prologue() and paste the original
instruction after the prologue.
Signed-off-by: Wang Nan <wangnan0@huawei.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1447675815-166222-12-git-send-email-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The output prologue for offn(...off2(off1(reg)))) should be:
r6 <- r1 // save ctx into a callee saved register
r7 <- fp
r7 <- r7 - stack_offset // pointer to result slot
/* load r3 with the offset in pt_regs of 'reg' */
(r7) <- r3 // make slot valid
r3 <- r3 + off1 // prepare to read unsafe pointer
r2 <- 8
r1 <- r7 // result put onto stack
call probe_read // read unsafe pointer
jnei r0, 0, err // error checking
r3 <- (r7) // read result
r3 <- r3 + off2 // prepare to read unsafe pointer
r2 <- 8
r1 <- r7
call probe_read
jnei r0, 0, err
...
/* load r2, r3, r4 from stack */
goto success
err:
r2 <- 1
/* load r3, r4, r5 with 0 */
goto usercode
success:
r2 <- 0
usercode:
r1 <- r6 // restore ctx
// original user code
If all of arguments reside in register (dereferencing is not
required), gen_prologue_fastpath() will be used to create
fast prologue:
r3 <- (r1 + offset of reg1)
r4 <- (r1 + offset of reg2)
r5 <- (r1 + offset of reg3)
r2 <- 0
P.S.
eBPF calling convention is defined as:
* r0 - return value from in-kernel function, and exit value
for eBPF program
* r1 - r5 - arguments from eBPF program to in-kernel function
* r6 - r9 - callee saved registers that in-kernel function will
preserve
* r10 - read-only frame pointer to access stack
Committer note:
At least testing if it builds and loads:
# cat test_probe_arg.c
struct pt_regs;
__attribute__((section("lock_page=__lock_page page->flags"), used))
int func(struct pt_regs *ctx, int err, unsigned long flags)
{
return 1;
}
char _license[] __attribute__((section("license"), used)) = "GPL";
int _version __attribute__((section("version"), used)) = 0x40300;
# perf record -e ./test_probe_arg.c usleep 1
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.016 MB perf.data ]
# perf evlist
perf_bpf_probe:lock_page
#
Signed-off-by: He Kuang <hekuang@huawei.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Wang Nan <wangnan0@huawei.com> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1447675815-166222-11-git-send-email-wangnan0@huawei.com Signed-off-by: Wang Nan <wangnan0@huawei.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
char _license[] __attribute__((section("license"), used)) = "GPL";
int _version __attribute__((section("version"), used)) = 0x40300;
#
# ./perf record -e ./test_probe_glob.c ls /
...
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.013 MB perf.data ]
# ./perf evlist
perf_bpf_probe:func_1
perf_bpf_probe:func
After changing "inlines=no" to "inlines=yes":
# ./perf record -e ./test_probe_glob.c ls /
...
[ perf record: Woken up 2 times to write data ]
[ perf record: Captured and wrote 0.013 MB perf.data ]
# ./perf evlist
perf_bpf_probe:func_3
perf_bpf_probe:func_2
perf_bpf_probe:func_1
perf_bpf_probe:func
# perf record -e ./test_probe_force.c usleep 1
Error: event "func" already exists.
Hint: Remove existing event by 'perf probe -d'
or force duplicates by 'perf probe -f'
or set 'force=yes' in BPF source.
event syntax error: './test_probe_force.c'
\___ Probe point exist. Try 'perf probe -d "*"' and set 'force=yes'
(add -v to see detail)
...
Then replace 'force=no' to 'force=yes':
# vim test_probe_force.c
# perf record -e ./test_probe_force.c usleep 1
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.017 MB perf.data ]
# perf evlist
perf_bpf_probe:func_1
perf_bpf_probe:func
#
Signed-off-by: Wang Nan <wangnan0@huawei.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1447675815-166222-7-git-send-email-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Wang Nan [Mon, 16 Nov 2015 12:10:06 +0000 (12:10 +0000)]
perf bpf: Allow attaching BPF programs to modules symbols
By extending the syntax of BPF object section names, this patch allows
users to attach BPF programs to symbols in modules. For example:
SEC("module=i915;"
"parse_cmds=i915_parse_cmds")
int parse_cmds(void *ctx)
{
return 1;
}
The implementation is very simple: like what 'perf probe' does, for module,
fill 'uprobe' field in 'struct perf_probe_event'. Other parts will be done
automatically.
Signed-off-by: Wang Nan <wangnan0@huawei.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Brendan Gregg <brendan.d.gregg@gmail.com> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: David Ahern <dsahern@gmail.com> Cc: He Kuang <hekuang@huawei.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kaixu Xia <xiakaixu@huawei.com> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1447675815-166222-5-git-send-email-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Where, in section name of a program, before the main config string, we
can use 'key=value' style options. Now the only option key is "exec",
for uprobes.
Signed-off-by: Wang Nan <wangnan0@huawei.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1447675815-166222-4-git-send-email-wangnan0@huawei.com
[ Changed the separator from \n to ; ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Wang Nan [Mon, 16 Nov 2015 12:10:11 +0000 (12:10 +0000)]
perf bpf: Compile dwarf-regs.c if CONFIG_BPF_PROLOGUE is on
regs_query_register_offset() in dwarf-regs.c is required by BPF
prologue. This patch compiles it if CONFIG_BPF_PROLOGUE is on to avoid
build failure when CONFIG_BPF_PROLOGUE is on but CONFIG_DWARF is not
set.
Signed-off-by: He Kuang <hekuang@huawei.com> Acked-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: He Kuang <hekuang@huawei.com> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1447675815-166222-10-git-send-email-wangnan0@huawei.com Signed-off-by: Wang Nan <wangnan0@huawei.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Wang Nan [Mon, 16 Nov 2015 12:10:10 +0000 (12:10 +0000)]
perf bpf: Add BPF_PROLOGUE config options for further patches
If both LIBBPF and DWARF are detected, it is possible to create prologue
for eBPF programs to help them access kernel data. HAVE_BPF_PROLOGUE and
CONFIG_BPF_PROLOGUE are added as flags for this feature.
PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET is introduced in commit 63ab024a5b6f295ca17a293ad81b7c728f49a89a ("perf tools:
regs_query_register_offset() infrastructure"), which indicates that an
architecture supports converting name of a register to its offset in
'struct pt_regs'. Without this support, BPF_PROLOGUE should be turned
off.
Signed-off-by: Wang Nan <wangnan0@huawei.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1447675815-166222-9-git-send-email-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Wang Nan [Mon, 16 Nov 2015 12:10:09 +0000 (12:10 +0000)]
bpf tools: Load a program with different instances using preprocessor
This patch is a preparation for BPF prologue support which allows
generating a series of BPF bytecode for fetching kernel data before
calling program code. With the newly introduced multiple instances
support, perf is able to create different prologues for different kprobe
points.
Before this patch, a bpf_program can be loaded into kernel only once,
and get the only resulting fd. What this patch does is to allow creating
and loading different variants of one bpf_program, then fetching their
fds.
Here we describe the basic idea in this patch. The detailed description
of the newly introduced APIs can be found in comments in the patch body.
The key of this patch is the new mechanism in bpf_program__load().
Instead of loading BPF program into kernel directly, it calls a
'pre-processor' to generate program instances which would be finally
loaded into the kernel based on the original code. To enable the
generation of multiple instances, libbpf passes an index to the
pre-processor so it know which instance is being loaded.
Pre-processor should be called from libbpf's user (perf) using
bpf_program__set_prep(). The number of instances and the relationship
between indices and the target instance should be clear when calling
bpf_program__set_prep().
To retrieve a fd for a specific instance of a program,
bpf_program__nth_fd() is introduced. It returns the resulting fd
according to index.
Signed-off-by: He Kuang <hekuang@huawei.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: He Kuang <hekuang@huawei.com> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1447675815-166222-8-git-send-email-wangnan0@huawei.com Signed-off-by: Wang Nan <wangnan0@huawei.com>
[ Enclosed multi-line if/else blocks with {}, (*func_ptr)() -> func_ptr() ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Wang Nan [Mon, 16 Nov 2015 14:42:05 +0000 (11:42 -0300)]
tools: Clone the kernel's strtobool function
Copying it to tools/lib/string.c, the counterpart to the kernel's
lib/string.c.
This is preparation for enhancing BPF program configuration, which will
allow config string like 'inlines=yes'.
Signed-off-by: Wang Nan <wangnan0@huawei.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Jonathan Cameron <jic23@cam.ac.uk> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1447675815-166222-6-git-send-email-wangnan0@huawei.com
[ Copied it to tools/lib/string.c instead, to make it usable by other tools/ ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
tools: Adopt memdup() from tools/perf, moving it to tools/lib/string.c
That will contain more string functions with counterparts, sometimes
verbatim copies, in the kernel.
Acked-by: Wang Nan <wangnan0@huawei.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Link: http://lkml.kernel.org/n/tip-rah6g97kn21vfgmlramorz6o@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
perf test: Fix build of BPF and LLVM on older glibc libraries
$ rpm -q glibc
glibc-2.12-1.166.el6_7.1.x86_64
<SNIP>
CC /tmp/build/perf/tests/llvm.o
cc1: warnings being treated as errors
tests/llvm.c: In function ‘test_llvm__fetch_bpf_obj’:
tests/llvm.c:53: error: declaration of ‘index’ shadows a global declaration
/usr/include/string.h:489: error: shadowed declaration is here
<SNIP>
CC /tmp/build/perf/tests/bpf.o
cc1: warnings being treated as errors
tests/bpf.c: In function ‘__test__bpf’:
tests/bpf.c:149: error: declaration of ‘index’ shadows a global declaration
/usr/include/string.h:489: error: shadowed declaration is here
<SNIP>
Cc: He Kuang <hekuang@huawei.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: pi3orama@163.com Cc: Wang Nan <wangnan0@huawei.com> Cc: Zefan Li <lizefan@huawei.com> Fixes: b31de018a628 ("perf test: Enhance the LLVM test: update basic BPF test program") Fixes: ba1fae431e74 ("perf test: Add 'perf test BPF'") Link: http://lkml.kernel.org/n/tip-akpo4r750oya2phxoh9e3447@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Ingo Molnar [Wed, 18 Nov 2015 05:56:48 +0000 (06:56 +0100)]
Merge tag 'perf-urgent-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent
Pull perf/urgent fixes from Arnaldo Carvalho de Melo:
- Do not change the key of an object in a rbtree, this time it was
the one for DSOs lookup by its long_name, and the noticed symptom was
with 'perf buildid-list --with-hits' (Adrian Hunter)
- 'perf inject' is a pipe, events it doesn't touch should be passed
on, PERF_RECORD_LOST wasn't, fix it (Adrian Hunter)
- Make 'perf buildid-list' request event ordering, as it needs to
first get the mmap events to be able to mark wich DSOs had hits
(Adrian Hunter)
- Fix memory leaks on failure in 'perf probe' (Masami Hiramatsu, Wang Nan)
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@kernel.org>
Wang Nan [Fri, 13 Nov 2015 12:29:11 +0000 (12:29 +0000)]
perf probe: Clear probe_trace_event when add_probe_trace_event() fails
When probing with a glob, errors in add_probe_trace_event() won't be
passed to debuginfo__find_trace_events() because it would be modified by
probe_point_search_cb(). It causes a segfault if perf fails to find an
argument for a probe point matched by the glob. For example:
# ./perf probe -v -n 'SyS_dup? oldfd'
probe-definition(0): SyS_dup? oldfd
symbol:SyS_dup? file:(null) line:0 offset:0 return:0 lazy:(null)
parsing arg: oldfd into oldfd
1 arguments
Looking at the vmlinux_path (7 entries long)
Using /lib/modules/4.3.0-rc4+/build/vmlinux for symbols
Open Debuginfo file: /lib/modules/4.3.0-rc4+/build/vmlinux
Try to find probe point from debuginfo.
Matched function: SyS_dup3
found inline addr: 0xffffffff812095c0
Probe point found: SyS_dup3+0
Searching 'oldfd' variable in context.
Converting variable oldfd into trace event.
oldfd type is long int.
found inline addr: 0xffffffff812096d4
Probe point found: SyS_dup2+36
Searching 'oldfd' variable in context.
Failed to find 'oldfd' in this function.
Matched function: SyS_dup3
Probe point found: SyS_dup3+0
Searching 'oldfd' variable in context.
Converting variable oldfd into trace event.
oldfd type is long int.
Matched function: SyS_dup2
Probe point found: SyS_dup2+0
Searching 'oldfd' variable in context.
Converting variable oldfd into trace event.
oldfd type is long int.
Found 4 probe_trace_events.
Opening /sys/kernel/debug/tracing//kprobe_events write=1
Writing event: p:probe/SyS_dup3 _text+2135488 oldfd=%di:s64
Segmentation fault (core dumped)
#
This patch ensures that add_probe_trace_event() doesn't touches
tf->ntevs and tf->tevs if those functions fail.
After the patch:
# perf probe 'SyS_dup? oldfd'
Failed to find 'oldfd' in this function.
Added new events:
probe:SyS_dup3 (on SyS_dup? with oldfd)
probe:SyS_dup3_1 (on SyS_dup? with oldfd)
probe:SyS_dup2 (on SyS_dup? with oldfd)
You can now use it in all perf tools, such as:
perf record -e probe:SyS_dup2 -aR sleep 1
Signed-off-by: Wang Nan <wangnan0@huawei.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1447417761-156094-3-git-send-email-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Masami Hiramatsu [Fri, 13 Nov 2015 12:29:10 +0000 (12:29 +0000)]
perf probe: Fix memory leaking on failure by clearing all probe_trace_events
Fix memory leaking on the debuginfo__find_trace_events() failure path
which frees an array of probe_trace_events but doesn't clears all the
allocated sub-structures and strings.
So, before doing zfree(tevs), clear all the array elements which may
have allocated resources.
Reported-by: Wang Nan <wangnan0@huawei.com> Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1447417761-156094-2-git-send-email-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Adrian Hunter [Fri, 13 Nov 2015 09:48:31 +0000 (11:48 +0200)]
perf buildid-list: Requires ordered events
'perf buildid-list' processes events to determine hits (i.e. with-hits
option). That may not work if events are not sorted in order. i.e. MMAP
events must be processed before the samples that depend on them so that
sample processing can 'hit' the DSO to which the MMAP refers.
Adrian Hunter [Fri, 13 Nov 2015 09:48:30 +0000 (11:48 +0200)]
perf symbols: Fix dso lookup by long name and missing buildids
Commit 4598a0a6d22f ("perf symbols: Improve DSO long names lookup speed
with rbtree") Added a tree to lookup dsos by long name. That tree gets
corrupted whenever a dso long name is changed because the tree is not
updated.
One effect of that is buildid-list does not work with the 'with-hits'
option because dso lookup fails and results in two structs for the same
dso. The first has the buildid but no hits, the second has hits but no
buildid. e.g.
Before:
$ tools/perf/perf record ls
arch certs CREDITS Documentation firmware include
ipc Kconfig lib Makefile net REPORTING-BUGS
scripts sound usr block COPYING crypto
drivers fs init Kbuild kernel MAINTAINERS
mm README samples security tools virt
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.012 MB perf.data (11 samples) ]
$ tools/perf/perf buildid-list 574da826c66538a8d9060d393a8866289bd06005 [kernel.kallsyms] 30c94dc66a1fe95180c3d68d2b89e576d5ae213c /lib/x86_64-linux-gnu/libc-2.19.so
$ tools/perf/perf buildid-list -H 574da826c66538a8d9060d393a8866289bd06005 [kernel.kallsyms] 0000000000000000000000000000000000000000 /lib/x86_64-linux-gnu/libc-2.19.so
The fix is to record the root of the tree on the dso so that
dso__set_long_name() can update the tree when the long name changes.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Don Zickus <dzickus@redhat.com> Cc: Douglas Hatch <doug.hatch@hp.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Scott J Norton <scott.norton@hp.com> Cc: Waiman Long <Waiman.Long@hp.com> Fixes: 4598a0a6d22f ("perf symbols: Improve DSO long names lookup speed with rbtree") Link: http://lkml.kernel.org/r/1447408112-1920-2-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
perf symbols: Allow forcing reading of non-root owned files by root
When the root user tries to read a file owned by some other user we get:
# ls -la perf.data
-rw-------. 1 acme acme 20032 Nov 12 15:50 perf.data
# perf report
File perf.data not owned by current user or root (use -f to override)
# perf report -f | grep -v ^# | head -2
30.96% ls [kernel.vmlinux] [k] do_set_pte
28.24% ls libc-2.20.so [.] intel_check_word
#
That wasn't happening when the symbol code tried to read a JIT map,
where the same check was done but no forcing was possible, fix it.
Reported-by: Brendan Gregg <brendan.d.gregg@gmail.com> Tested-by: Brendan Gregg <brendan.d.gregg@gmail.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://permalink.gmane.org/gmane.linux.kernel.perf.user/2380 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
perf hists browser: The dso can be obtained from popup_action->ms.map->dso
So no need to have a 'dso' member in 'popup_action', remove it as no
code is using it, already.
Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-76a6s0007slug0op0wkl6o8b@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
perf hists browser: Fix 'd' hotkey action to filter by DSO
When pressing 'd' the expected action is to filter all entries by the
DSO in the current entry, but for that the action->map needs to be set,
and only action->dso was being set, fix it.
Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Fixes: 045b80dd0340 ("perf hists browser: Use the map to determine if a DSO is being used as a kernel") Link: http://lkml.kernel.org/n/tip-xqhfzgoblq49lk5h5u82atro@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Adrian Hunter [Fri, 6 Nov 2015 13:59:29 +0000 (15:59 +0200)]
perf symbols: Rebuild rbtree when adjusting symbols for kcore
Normally symbols are read from the DSO and adjusted, if need be, so that
the symbol start matches the file offset in the DSO file (we want the
file offset because that is what we know from MMAP events). That is done
by dso__load_sym() which inserts the symbols *after* adjusting them.
In the case of kcore, the symbols have been read from kallsyms and the
symbol start is the memory address. The symbols have to be adjusted to
match the kcore file offsets. dso__split_kallsyms_for_kcore() does that,
but now the adjustment is being done *after* the symbols have been
inserted. It appears dso__split_kallsyms_for_kcore() was assuming that
changing the symbol start would not change the order in the rbtree -
which is, of course, not guaranteed.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Tested-by: Wang Nan <wangnan0@huawei.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/563CB241.2090701@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Ingo Molnar [Thu, 12 Nov 2015 06:37:53 +0000 (07:37 +0100)]
Merge tag 'perf-urgent-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent
Pull perf/urgent fixes from Arnaldo Carvalho de Melo:
- Add missing newlines to some pr_err() calls (Arnaldo Carvalho de Melo)
- Print full source file paths when using
'perf annotate --print-line --full-paths' (Michael Petlan)
- Fix 'perf probe -d' when just one out of uprobes and kprobes is
enabled (Wang Nan)
- Add compiler.h to list.h to fix 'make perf-tar-src-pkg' generated
tarballs, i.e. out of tree building (Arnaldo Carvalho de Melo)
- Add the llvm-src-base.c and llvm-src-kbuild.c files, generated by the
'perf test' LLVM entries, when running it in-tree, to .gitignore (Yunlong Song)
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@kernel.org>
list.h needs WRITE_ONCE() since 7f5f873c6a07 ("rculist: Use WRITE_ONCE()
when deleting from reader-visible list") add it before including the
kernel's list.h file.
This fixes builds of 'make perf-tar-src-pkg' perf tool tarball builds,
i.e. out of tree builds.
Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-e0rb8f7jwz0jn24ttyick9u6@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Wang Nan [Fri, 6 Nov 2015 09:50:15 +0000 (09:50 +0000)]
perf probe: Verify parameters in two functions
On kernel with only one out of CONFIG_KPROBE_EVENTS and
CONFIG_UPROBE_EVENTS enabled, 'perf probe -d' causes a segfault because
perf_del_probe_events() calls probe_file__get_events() with a negative
fd.
This patch fixes it by adding parameter validation at the entry of
probe_file__get_events() and probe_file__get_rawlist(). Since they are
both non-static public functions (in .h file), parameter verifying is
required.
v1 -> v2: Verify fd at the head of probe_file__get_rawlist() instead of
checking at call site (suggested by Masami and Arnaldo at [1,2]).
Signed-off-by: Wang Nan <wangnan0@huawei.com> Acked-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1446803415-83382-1-git-send-email-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
perf session: Add missing newlines to some pr_err() calls
Before:
[acme@zoo linux]$ perf evlist
WARNING: The perf.data file's data size field is 0 which is unexpected.
Was the 'perf record' command properly terminated?
non matching sample_type[acme@zoo linux]$
After:
[acme@zoo linux]$ perf evlist
WARNING: The perf.data file's data size field is 0 which is unexpected.
Was the 'perf record' command properly terminated?
non matching sample_type
[acme@zoo linux]$
Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-wscok3a2s7yrj8156oc2r6qe@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Michael Petlan [Mon, 9 Nov 2015 15:33:31 +0000 (16:33 +0100)]
perf annotate: Support full source file paths for srcline fix
The --full-paths option did not show the full source file paths in the 'perf
annotate' tool, because the value of the option was not propagated into the
related functions.
With this patch the value of the --full-paths option is known to the function
that composes the srcline string, so it prints the full path when necessary.
Committer Note:
This affects annotate when the --print-line option is used:
Yunlong Song [Mon, 9 Nov 2015 03:10:03 +0000 (11:10 +0800)]
perf test: Add llvm-src-base.c and llvm-src-kbuild.c to .gitignore
Commit b31de018a6284a25e0fdfeb028e724f8417ec3b1 ("perf test: Enhance the
LLVM test: update basic BPF test program") dynamically creates file
llvm-src-base.c during the perf building.
Similarly, the commit 7af3f3d55b80cce40ad94b6b8e173dccedaf25e6 ("perf
test: Enhance the LLVM tests: add kbuild test") dynamically creates file
llvm-src-kbuild.c during the perf building. Add them to .gitignore.
Signed-off-by: Yunlong Song <yunlong.song@huawei.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@intel.com> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Wang Nan <wangnan0@huawei.com> Fixes: b31de018a628 ("perf test: Enhance the LLVM test: update basic BPF test program") Fixes: 7af3f3d55b80 ("perf test: Enhance the LLVM tests: add kbuild test") Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Peter Zijlstra [Mon, 2 Nov 2015 09:50:51 +0000 (10:50 +0100)]
perf: Fix inherited events vs. tracepoint filters
Arnaldo reported that tracepoint filters seem to misbehave (ie. not
apply) on inherited events.
The fix is obvious; filters are only set on the actual (parent)
event, use the normal pattern of using this parent event for filters.
This is safe because each child event has a reference to it.
Reported-by: Arnaldo Carvalho de Melo <acme@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@kernel.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Wang Nan <wangnan0@huawei.com> Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/20151102095051.GN17308@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
perf: Disable IRQs across RCU RS CS that acquires scheduler lock
The perf_lock_task_context() function disables preemption across its
RCU read-side critical section because that critical section acquires
a scheduler lock. If there was a preemption during that RCU read-side
critical section, the rcu_read_unlock() could attempt to acquire scheduler
locks, resulting in deadlock.
However, recent optimizations to expedited grace periods mean that IPI
handlers that execute during preemptible RCU read-side critical sections
can now cause the subsequent rcu_read_unlock() to acquire scheduler locks.
Disabling preemption does nothiing to prevent these IPI handlers from
executing, so these optimizations introduced a deadlock. In theory,
this deadlock could be avoided by pulling all wakeups and printk()s out
from rnp->lock critical sections, but in practice this would re-introduce
some RCU CPU stall warning bugs.
Given that acquiring scheduler locks entails disabling interrupts, these
deadlocks can be avoided by disabling interrupts (instead of disabling
preemption) across any RCU read-side critical that acquires scheduler
locks and holds them across the rcu_read_unlock(). This commit therefore
makes this change for perf_lock_task_context().
Reported-by: Dave Jones <davej@codemonkey.org.uk> Reported-by: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Stephane Eranian <eranian@gmail.com> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/20151104134838.GR29027@linux.vnet.ibm.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
Ingo Molnar [Sun, 8 Nov 2015 07:22:37 +0000 (08:22 +0100)]
Merge tag 'perf-core-for-mingo-2' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent
Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:
Fixes:
- libbpf error reporting improvements, using a strerror interface to
more precisely tell the user about problems with the provided
scriptlet, be it in C or as a ready made object file (Wang Nan)
- Do not be case sensitive when searching for matching 'perf test'
entries (Arnaldo Carvalho de Melo)
- Inform the user about objdump failures in 'perf annotate' (Andi Kleen)
Infrastructure changes:
- Improve the LLVM 'perf test' entry, introduce a new ones for
BPF and kbuild tests to check the environment used by clang to
compile .c scriptlets (Wang Nan)
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@kernel.org>
perf test: Do not be case sensitive when searching for matching tests
Before:
# perf test llvm
# perf test LLVM
35: Test LLVM searching and compiling : Ok
#
After
# perf test llvm
35: Test LLVM searching and compiling : Ok
#
Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-c1u05npqbf6epse17ovfejoj@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Wang Nan [Fri, 6 Nov 2015 13:49:43 +0000 (13:49 +0000)]
perf test: Add 'perf test BPF'
This patch adds BPF testcase for testing BPF event filtering.
By utilizing the result of 'perf test LLVM', this patch compiles the
eBPF sample program then test its ability. The BPF script in 'perf test
LLVM' lets only 50% samples generated by epoll_pwait() to be captured.
This patch runs that system call for 111 times, so the result should
contain 56 samples.
Signed-off-by: Wang Nan <wangnan0@huawei.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1446817783-86722-8-git-send-email-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Wang Nan [Fri, 6 Nov 2015 13:49:42 +0000 (13:49 +0000)]
perf test: Enhance the LLVM tests: add kbuild test
This patch adds a kbuild testcase to check whether kernel headers can be
correctly found.
For example:
# mv /lib/modules/4.3.0-rc5{,.bak}
# perf test LLVM
38: Test LLVM searching and compiling : Skip
# perf test -v LLVM
...
<stdin>:11:10: fatal error: 'uapi/linux/fs.h' file not found
#include <uapi/linux/fs.h>
^
1 error generated.
ERROR: unable to compile -
Hint: Check error message shown above.
Hint: You can also pre-compile it into .o using:
clang -target bpf -O2 -c -
with proper -I and -D options.
Failed to compile test case: 'Test kbuild searching'
test child finished with -2
Signed-off-by: Wang Nan <wangnan0@huawei.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1446817783-86722-7-git-send-email-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Wang Nan [Fri, 6 Nov 2015 13:49:41 +0000 (13:49 +0000)]
perf test: Enhance the LLVM test: update basic BPF test program
This patch replaces the original toy BPF program with the previously
introduced bpf-script-example.c. Dynamically embeddeding it into
'llvm-src-base.c'.
The newly introduced BPF program attaches a BPF program to
'sys_epoll_pwait()'. perf itself never use that syscall, so further test
can verify their result with it. The program would generate 1 sample in
every 2 calls of epoll_pwait() system call.
Since the resulting BPF object is useful per se for further tests,
test_llvm__fetch_bpf_obj() is introduced for creating BPF objects from
source. The LLVM test was rewritten to use it.
Committer note:
Running it:
[root@zoo wb]# perf test -v LLVM
35: Test LLVM searching and compiling :
--- start ---
test child forked, pid 17740
Kernel build dir is set to /lib/modules/4.3.0-rc1+/build
set env: KBUILD_DIR=/lib/modules/4.3.0-rc1+/build
unset env: KBUILD_OPTS
include option is set to -nostdinc -isystem /usr/lib/gcc/x86_64-redhat-linux/4.9.2/include -I/home/git/linux/arch/x86/include -Iarch/x86/include/generated/uapi -Iarch/x86/include/generated -I/home/git/linux/include -Iinclude -I/home/git/linux/arch/x86/include/uapi -Iarch/x86/include/generated/uapi -I/home/git/linux/include/uapi -Iinclude/generated/uapi -include /home/git/linux/include/linux/kconfig.h
set env: NR_CPUS=4
set env: LINUX_VERSION_CODE=0x40300
set env: CLANG_EXEC=/usr/libexec/icecc/bin/clang
set env: CLANG_OPTIONS=-xc
set env: KERNEL_INC_OPTIONS= -nostdinc -isystem /usr/lib/gcc/x86_64-redhat-linux/4.9.2/include -I/home/git/linux/arch/x86/include -Iarch/x86/include/generated/uapi -Iarch/x86/include/generated -I/home/git/linux/include -Iinclude -I/home/git/linux/arch/x86/include/uapi -Iarch/x86/include/generated/uapi -I/home/git/linux/include/uapi -Iinclude/generated/uapi -include /home/git/linux/include/linux/kconfig.h
set env: WORKING_DIR=/lib/modules/4.3.0-rc1+/build
set env: CLANG_SOURCE=-
llvm compiling command template: echo '/*
* bpf-script-example.c
* Test basic LLVM building
*/
#ifndef LINUX_VERSION_CODE
# error Need LINUX_VERSION_CODE
# error Example: for 4.2 kernel, put 'clang-opt="-DLINUX_VERSION_CODE=0x40200" into llvm section of ~/.perfconfig'
#endif
#define BPF_ANY 0
#define BPF_MAP_TYPE_ARRAY 2
#define BPF_FUNC_map_lookup_elem 1
#define BPF_FUNC_map_update_elem 2
SEC("func=sys_epoll_pwait")
int bpf_func__sys_epoll_pwait(void *ctx)
{
int ind =0;
int *flag = bpf_map_lookup_elem(&flip_table, &ind);
int new_flag;
if (!flag)
return 0;
/* flip flag and store back */
new_flag = !*flag;
bpf_map_update_elem(&flip_table, &ind, &new_flag, BPF_ANY);
return new_flag;
}
char _license[] SEC("license") = "GPL";
int _version SEC("version") = LINUX_VERSION_CODE;
' | $CLANG_EXEC -D__KERNEL__ -D__NR_CPUS__=$NR_CPUS -DLINUX_VERSION_CODE=$LINUX_VERSION_CODE $CLANG_OPTIONS $KERNEL_INC_OPTIONS -Wno-unused-value -Wno-pointer-sign -working-directory $WORKING_DIR -c "$CLANG_SOURCE" -target bpf -O2 -o -
test child finished with 0
---- end ----
Test LLVM searching and compiling: Ok
[root@zoo wb]#
Signed-off-by: Wang Nan <wangnan0@huawei.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1446817783-86722-6-git-send-email-wangnan0@huawei.com Signed-off-by: He Kuang <hekuang@huawei.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Wang Nan [Fri, 6 Nov 2015 13:58:09 +0000 (13:58 +0000)]
perf bpf: Improve BPF related error messages
A series of bpf loader related error codes were introduced to help error
reporting. Functions were improved to return these new error codes.
Functions which return pointers were adjusted to encode error codes into
return value using the ERR_PTR() interface.
bpf_loader_strerror() was improved to convert these error messages to
strings. It checks the error codes and calls libbpf_strerror() and
strerror_r() accordingly, so caller don't need to consider checking the
range of the error code.
In bpf__strerror_load(), print kernel version of running kernel and the
object's 'version' section to notify user how to fix his/her program.
v1 -> v2:
Use macro for error code.
Fetch error message based on array index, eliminate for-loop.
Print version strings.
Before:
# perf record -e ./test_kversion_nomatch_program.o sleep 1
event syntax error: './test_kversion_nomatch_program.o'
\___ Failed to load program: Validate your program and check 'license'/'version' sections in your object
SKIP
After:
# perf record -e ./test_kversion_nomatch_program.o ls
event syntax error: './test_kversion_nomatch_program.o'
\___ 'version' (4.4.0) doesn't match running kernel (4.3.0)
SKIP
Signed-off-by: Wang Nan <wangnan0@huawei.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1446818289-87444-1-git-send-email-wangnan0@huawei.com
[ Add 'static inline' to bpf__strerror_prepare_load() when LIBBPF is disabled ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Wang Nan [Fri, 6 Nov 2015 13:55:35 +0000 (13:55 +0000)]
perf tools: Make fetch_kernel_version() publicly available
There are 2 places in llvm-utils.c which find kernel version information
through uname. This patch extracts the uname related code into a
fetch_kernel_version() function and puts it into util.h so it can be
reused.
Signed-off-by: Wang Nan <wangnan0@huawei.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1446818135-87310-1-git-send-email-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Wang Nan [Fri, 6 Nov 2015 13:49:38 +0000 (13:49 +0000)]
bpf tools: Add new API bpf_object__get_kversion()
bpf_object__get_kversion() can be used to fetch value of object's
'version' section. Following patch will use it for error reporting.
Signed-off-by: Wang Nan <wangnan0@huawei.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1446817783-86722-3-git-send-email-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Wang Nan [Fri, 6 Nov 2015 13:49:37 +0000 (13:49 +0000)]
bpf tools: Improve libbpf error reporting
In this patch, a series of libbpf specific error numbers and
libbpf_strerror() are introduced to help reporting errors.
Functions are updated to pass correct the error number through the
CHECK_ERR() macro.
All users of bpf_object__open{_buffer}() and bpf_program__title() in
perf are modified accordingly. In addition, due to the error codes
changing, bpf__strerror_load() is also modified to use them.
bpf__strerror_head() is also changed accordingly so it can parse libbpf
errors. bpf_loader_strerror() is introduced for that purpose, and will
be improved by the following patch.
load_program() is improved not to dump log buffer if it is empty. log
buffer is also used to deduce whether the error was caused by an invalid
program or other problem.
v1 -> v2:
- Using macro for error code.
- Fetch error message based on array index, eliminate for-loop.
- Use log buffer to detect the reason of failure. 3 new error code
are introduced to replace LIBBPF_ERRNO__LOAD.
In v1:
# perf record -e ./test_ill_program.o ls
event syntax error: './test_ill_program.o'
\___ Failed to load program: Validate your program and check 'license'/'version' sections in your object
SKIP
# perf record -e ./test_kversion_nomatch_program.o ls
event syntax error: './test_kversion_nomatch_program.o'
\___ Failed to load program: Validate your program and check 'license'/'version' sections in your object
SKIP
# perf record -e ./test_big_program.o ls
event syntax error: './test_big_program.o'
\___ Failed to load program: Validate your program and check 'license'/'version' sections in your object
SKIP
In v2:
# perf record -e ./test_ill_program.o ls
event syntax error: './test_ill_program.o'
\___ Kernel verifier blocks program loading
SKIP
# perf record -e ./test_kversion_nomatch_program.o
event syntax error: './test_kversion_nomatch_program.o'
\___ Incorrect kernel version
SKIP
(Will be further improved by following patches)
# perf record -e ./test_big_program.o
event syntax error: './test_big_program.o'
\___ Program too big
SKIP
Signed-off-by: Wang Nan <wangnan0@huawei.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1446817783-86722-2-git-send-email-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
perf probe: Cleanup find_perf_probe_point_from_map to reduce redundancy
In find_perf_probe_point_from_map(), the 'ret' variable is initialized
with -ENOENT but overwritten by the return code of
kernel_get_symbol_address_by_name(), and after that it is re-initialized
with -ENOENT again.
Setting ret=-ENOENT twice looks a bit redundant. This avoids the
overwriting and just returns -ENOENT if some error happens to simplify
the code.
Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Cc: Zefan Li <lizefan@huawei.com> Link: http://lkml.kernel.org/n/tip-ufp1zgbktzmttcputozneomd@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Andi Kleen [Fri, 6 Nov 2015 03:06:07 +0000 (19:06 -0800)]
perf annotate: Inform the user about objdump failures in --stdio
When the browser fails to annotate it is difficult for users to find out
what went wrong.
Add some errors for objdump failures that are displayed in the UI.
Note it would be even better to handle these errors smarter, like
falling back to the binary when the debug info is somehow corrupted. But
for now just giving a better error is an improvement.
Committer note:
This works for --stdio, where errors just scroll by the screen:
And with that one can use that command line to try to find out more about what
happened instead of getting a blank screen, an improvement.
We need tho to improve this further to get it to work with other UIs, like
--tui and --gtk, where it continues showing a blank screen, no messages, as
the pr_err() used is enough just for --stdio.
Signed-off-by: Andi Kleen <ak@linux.intel.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: http://lkml.kernel.org/r/1446779167-18949-1-git-send-email-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Jiri Olsa [Thu, 5 Nov 2015 14:40:45 +0000 (15:40 +0100)]
perf stat: Make stat options global
So they can be used in perf stat record command in following patch.
Signed-off-by: Jiri Olsa <jolsa@kernel.org> Tested-by: Kan Liang <kan.liang@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1446734469-11352-2-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Jiri Olsa [Mon, 2 Nov 2015 11:10:25 +0000 (12:10 +0100)]
perf sched latency: Fix thread pid reuse issue
The latency subcommand holds a tree of working atoms sorted by thread's
pid/tid. If there's new thread with same pid and tid, the old working atom is
found and assert bug condition is hit in search function:
Changing the sort function to use thread object pointers together with pid and
tid check. This way new thread will never find old one with same pid/tid.
Wang Nan [Thu, 5 Nov 2015 13:19:25 +0000 (13:19 +0000)]
perf tools: Fix find_perf_probe_point_from_map() which incorrectly returns success
It is possible that find_perf_probe_point_from_map() fails to find a
symbol but still returns 0 because of an small error when coding:
find_perf_probe_point_from_map() set 'ret' to error code at first, but
also use it to hold return value of kernel_get_symbol_address_by_name().
This patch resets 'ret' to error even kernel_get_symbol_address_by_name()
success, so if !sym, the whole function returns error correctly.
Signed-off-by: Wang Nan <wangnan0@huawei.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1446729565-27592-3-git-send-email-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Peter Feiner [Wed, 4 Nov 2015 17:21:46 +0000 (09:21 -0800)]
perf trace: Fix documentation for -i
The -i flag was incorrectly listed as a short flag for --no-inherit. It
should have only been listed as a short flag for --input.
This documentation error has existed since the --input flag was
introduced in 6810fc915f7a89d8134edb3996dbbf8eac386c26 (perf trace: Add
option to analyze events in a file versus live).
Signed-off-by: Peter Feiner <pfeiner@google.com> Cc: David Ahern <dsahern@gmail.com> Link: http://lkml.kernel.org/r/1446657706-14518-1-git-send-email-pfeiner@google.com Fixes: 6810fc915f7a ("perf trace: Add option to analyze events in a file versus live") Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Yunlong Song [Thu, 5 Nov 2015 06:56:34 +0000 (14:56 +0800)]
tools lib bpf: Change FEATURE-DUMP to FEATURE-DUMP.libbpf
Commit ed63f34c026e9a60d17fa750ecdfe3f600d49393 ("perf tools: Make perf
depend on libbpf") triggers the build of libbpf when building the perf
tools, dynamically creating FEATURE-DUMP.libbpf.
It failed to update the tools/lib/bpf/.gitignore file to have that
prefix, fix it.
Signed-off-by: Yunlong Song <yunlong.song@huawei.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@intel.com> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Wang Nan <wangnan0@huawei.com> Fixes: 65f041bee783 ("tools lib bpf: Use FEATURE_USER to allow building in the same dir as perf") Link: http://lkml.kernel.org/r/1446706594-4142-1-git-send-email-yunlong.song@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Wang Nan [Wed, 4 Nov 2015 11:20:05 +0000 (11:20 +0000)]
perf llvm: Pass LINUX_VERSION_CODE to BPF program when compiling
Arnaldo suggests to make LINUX_VERSION_CODE works like __func__ and
__FILE__ so user don't need to care setting right linux version too
much. In this patch, perf llvm transfers LINUX_VERSION_CODE macro
through clang cmdline.
Wang Nan [Wed, 4 Nov 2015 11:20:04 +0000 (11:20 +0000)]
perf llvm: Pass number of configured CPUs to clang compiler
This patch introduces a new macro "__NR_CPUS__" to perf's embedded clang
compiler, which represent the number of configured CPUs in this system.
BPF programs can use this macro to create a map with the same number of
system CPUs. For example:
Those tests take a long time and sometimes we stop it, so allow randomly
shuffling the tests so that we have a better chance of running more of
them in partial 'make build-test' runs.
Using it just on the 'build-test' target, i.e.:
make -C tools/perf build-test
Is equivalent to:
make SHUF=1 -C tools/perf -f tests/make
Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-ey7461i9q4k8u0987j8guun6@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Jiri Olsa [Wed, 4 Nov 2015 14:08:11 +0000 (15:08 +0100)]
perf tools: Insert split maps correctly into origin group
When new maps are cloned out of split map they are added into origin
map's group, but their groups pointer is not updated.
This could lead to a segfault, because map->groups is expected to be
always set as reported by Markus:
__map__is_kernel (map=map@entry=0x1abb7a0) at util/map.c:238
238 return __machine__kernel_map(map->groups->machine, map->type) =
(gdb) bt
#0 __map__is_kernel (map=map@entry=0x1abb7a0) at util/map.c:238
#1 0x00000000004393e4 in symbol_filter (map=map@entry=0x1abb7a0, sym=sym@entry
#2 0x00000000004fcd4d in dso__load_sym (dso=dso@entry=0x166dae0, map=map@entry
#3 0x00000000004a64e0 in dso__load (dso=0x166dae0, map=map@entry=0x1abb7a0, fi
#4 0x00000000004b941f in map__load (filter=0x4393c0 <symbol_filter>, map=<opti
#5 map__find_symbol (map=0x1abb7a0, addr=40188, filter=0x4393c0 <symbol_filter
...
Adding __map_groups__insert function to add map into groups together
with map->groups pointer update. It takes no lock as opposed to existing
map_groups__insert, as maps__fixup_overlappings(), where it is being
called, already has the necessary lock held.
Using __map_groups__insert to add new maps after map split.
Reported-by: Markus Trippelsdorf <markus@trippelsdorf.de> Signed-off-by: Jiri Olsa <jolsa@kernel.org> Tested-by: Markus Trippelsdorf <markus@trippelsdorf.de> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/20151104140811.GA32664@krava.brq.redhat.com Fixes: cfc5acd4c80b ("perf top: Filter symbols based on __map__is_kernel(map)") Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Linus Torvalds [Wed, 4 Nov 2015 05:33:18 +0000 (21:33 -0800)]
Merge branch 'x86-platform-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 platform changes from Ingo Molnar:
"Misc updates to the Intel MID and SGI UV platforms"
* 'x86-platform-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/intel-mid: Make intel_mid_ops static
arch/x86/intel-mid: Use kmemdup rather than duplicating its implementation
x86/platform/uv: Implement simple dump failover if kdump fails
x86/platform/uv: Insert per_cpu accessor function on uv_hub_nmi
Linus Torvalds [Wed, 4 Nov 2015 05:23:56 +0000 (21:23 -0800)]
Merge branch 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 mm changes from Ingo Molnar:
"The main changes are: continued PAT work by Toshi Kani, plus a new
boot time warning about insecure RWX kernel mappings, by Stephen
Smalley.
The new CONFIG_DEBUG_WX=y warning is marked default-y if
CONFIG_DEBUG_RODATA=y is already eanbled, as a special exception, as
these bugs are hard to notice and this check already found several
live bugs"
* 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/mm: Warn on W^X mappings
x86/mm: Fix no-change case in try_preserve_large_page()
x86/mm: Fix __split_large_page() to handle large PAT bit
x86/mm: Fix try_preserve_large_page() to handle large PAT bit
x86/mm: Fix gup_huge_p?d() to handle large PAT bit
x86/mm: Fix slow_virt_to_phys() to handle large PAT bit
x86/mm: Fix page table dump to show PAT bit
x86/asm: Add pud_pgprot() and pmd_pgprot()
x86/asm: Fix pud/pmd interfaces to handle large PAT bit
x86/asm: Add pud/pmd mask interfaces to handle large PAT bit
x86/asm: Move PUD_PAGE macros to page_types.h
x86/vdso32: Define PGTABLE_LEVELS to 32bit VDSO
Linus Torvalds [Wed, 4 Nov 2015 05:05:40 +0000 (21:05 -0800)]
Merge branch 'x86-headers-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 sigcontext header cleanups from Ingo Molnar:
"This series reorganizes and cleans up various aspects of the main
sigcontext UAPI headers, such as unifying the data structures and
updating/adding lots of comments to explain all the ABI details and
quirks. The headers can now also be built in user-space standalone"
* 'x86-headers-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/headers: Clean up too long lines
x86/headers: Remove <asm/sigcontext.h> references on the kernel side
x86/headers: Remove direct sigcontext32.h uses
x86/headers: Convert sigcontext_ia32 uses to sigcontext_32
x86/headers: Unify 'struct sigcontext_ia32' and 'struct sigcontext_32'
x86/headers: Make sigcontext pointers bit independent
x86/headers: Move the 'struct sigcontext' definitions into the UAPI header
x86/headers: Clean up the kernel's struct sigcontext types to be ABI-clean
x86/headers: Convert uses of _fpstate_ia32 to _fpstate_32
x86/headers: Unify 'struct _fpstate_ia32' and i386 struct _fpstate
x86/headers: Unify register type definitions between 32-bit compat and i386
x86/headers: Use ABI types consistently in sigcontext*.h
x86/headers: Separate out legacy user-space structure definitions
x86/headers: Clean up and better document uapi/asm/sigcontext.h
x86/headers: Clean up uapi/asm/sigcontext32.h
x86/headers: Fix (old) header file dependency bug in uapi/asm/sigcontext32.h
Linus Torvalds [Wed, 4 Nov 2015 03:39:42 +0000 (19:39 -0800)]
Merge branch 'x86-cpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 cpu changes from Ingo Molnar:
"Two changes in this cycle: a Kconfig help text enhancement, and an AMD
CLZERO instruction capability detection and enumeration"
* 'x86-cpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/cpu: Add CLZERO detection
x86/Kconfig/cpus: Fix/complete CPU type help texts
Linus Torvalds [Wed, 4 Nov 2015 03:34:22 +0000 (19:34 -0800)]
Merge branch 'x86-cleanups-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 cleanups from Ingo Molnar:
"An early_printk cleanup plus deinlining enhancements"
* 'x86-cleanups-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/early_printk: Set __iomem address space for IO
x86/signal: Deinline get_sigframe, save 240 bytes
x86: Deinline early_console_register, save 403 bytes
x86/e820: Deinline e820_type_to_string, save 126 bytes
Linus Torvalds [Wed, 4 Nov 2015 02:59:10 +0000 (18:59 -0800)]
Merge branch 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 asm changes from Ingo Molnar:
"The main change in this cycle is another step in the big x86 system
call interface rework by Andy Lutomirski, which moves most of the low
level x86 entry code from assembly to C, for all syscall entries
except native 64-bit system calls:
... our hope is that the final remaining step (converting native
64-bit system calls) will be less painful as all the previous steps,
given that most of the legacies and quirks are concentrated around
native 32-bit and compat environments"
* 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (47 commits)
x86/entry/32: Fix FS and GS restore in opportunistic SYSEXIT
x86/entry/32: Fix entry_INT80_32() to expect interrupts to be on
um/x86: Fix build after x86 syscall changes
x86/asm: Remove the xyz_cfi macros from dwarf2.h
selftests/x86: Style fixes for the 'unwind_vdso' test
x86/entry/64/compat: Document sysenter_fix_flags's reason for existence
x86/entry: Split and inline syscall_return_slowpath()
x86/entry: Split and inline prepare_exit_to_usermode()
x86/entry: Use pt_regs_to_thread_info() in syscall entry tracing
x86/entry: Hide two syscall entry assertions behind CONFIG_DEBUG_ENTRY
x86/entry: Micro-optimize compat fast syscall arg fetch
x86/entry: Force inlining of 32-bit syscall code
x86/entry: Make irqs_disabled checks in exit code depend on lockdep
x86/entry: Remove unnecessary IRQ twiddling in fast 32-bit syscalls
x86/asm: Remove thread_info.sysenter_return
x86/entry/32: Re-implement SYSENTER using the new C path
x86/entry/32: Switch INT80 to the new C syscall path
x86/entry/32: Open-code return tracking from fork and kthreads
x86/entry/compat: Implement opportunistic SYSRETL for compat syscalls
x86/vdso/compat: Wire up SYSENTER and SYSCSALL for compat userspace
...
Linus Torvalds [Wed, 4 Nov 2015 02:33:15 +0000 (18:33 -0800)]
Merge branch 'x86-apic-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 apic changes from Ingo Molnar:
"The main changes in this cycle were:
- Numachip updates: new hardware support, fixes and cleanups.
(Daniel J Blueman)
- misc smaller cleanups and fixlets"
* 'x86-apic-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/io_apic: Make eoi_ioapic_pin() static
x86/irq: Drop unlikely before IS_ERR_OR_NULL
x86/x2apic: Make stub functions available even if !CONFIG_X86_LOCAL_APIC
x86/apic: Deinline various functions
x86/numachip: Fix timer build conflict
x86/numachip: Introduce Numachip2 timer mechanisms
x86/numachip: Add Numachip IPI optimisations
x86/numachip: Add Numachip2 APIC support
x86/numachip: Cleanup Numachip support
Linus Torvalds [Wed, 4 Nov 2015 02:03:50 +0000 (18:03 -0800)]
Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull scheduler changes from Ingo Molnar:
"The main changes in this cycle were:
- sched/fair load tracking fixes and cleanups (Byungchul Park)
- Make load tracking frequency scale invariant (Dietmar Eggemann)
- sched/deadline updates (Juri Lelli)
- stop machine fixes, cleanups and enhancements for bugs triggered by
CPU hotplug stress testing (Oleg Nesterov)
- scheduler preemption code rework: remove PREEMPT_ACTIVE and related
cleanups (Peter Zijlstra)
- Rework the sched_info::run_delay code to fix races (Peter Zijlstra)
- Optimize per entity utilization tracking (Peter Zijlstra)
- ... misc other fixes, cleanups and smaller updates"
* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (57 commits)
sched: Don't scan all-offline ->cpus_allowed twice if !CONFIG_CPUSETS
sched: Move cpu_active() tests from stop_two_cpus() into migrate_swap_stop()
sched: Start stopper early
stop_machine: Kill cpu_stop_threads->setup() and cpu_stop_unpark()
stop_machine: Kill smp_hotplug_thread->pre_unpark, introduce stop_machine_unpark()
stop_machine: Change cpu_stop_queue_two_works() to rely on stopper->enabled
stop_machine: Introduce __cpu_stop_queue_work() and cpu_stop_queue_two_works()
stop_machine: Ensure that a queued callback will be called before cpu_stop_park()
sched/x86: Fix typo in __switch_to() comments
sched/core: Remove a parameter in the migrate_task_rq() function
sched/core: Drop unlikely behind BUG_ON()
sched/core: Fix task and run queue sched_info::run_delay inconsistencies
sched/numa: Fix task_tick_fair() from disabling numa_balancing
sched/core: Add preempt_count invariant check
sched/core: More notrace annotations
sched/core: Kill PREEMPT_ACTIVE
sched/core, sched/x86: Kill thread_info::saved_preempt_count
sched/core: Simplify preempt_count tests
sched/core: Robustify preemption leak checks
sched/core: Stop setting PREEMPT_ACTIVE
...
- Fix MCE and CPU hotplug interaction bug. (Ashok Raj)
- kcrash bootup robustness fix. (Baoquan He)
- kcrash cleanups. (Borislav Petkov)
- x86 microcode driver rework: simplify it by unmodularizing it and
other cleanups. (Borislav Petkov)"
* 'ras-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (23 commits)
x86/mce: Add a default case to the switch in __mcheck_cpu_ancient_init()
x86/mce: Add a Scalable MCA vendor flags bit
MAINTAINERS: Unify the microcode driver section
x86/microcode/intel: Move #ifdef DEBUG inside the function
x86/microcode/amd: Remove maintainers from comments
x86/microcode: Remove modularization leftovers
x86/microcode: Merge the early microcode loader
x86/microcode: Unmodularize the microcode driver
x86/mce: Fix thermal throttling reporting after kexec
kexec/crash: Say which char is the unrecognized
x86/setup/crash: Check memblock_reserve() retval
x86/setup/crash: Cleanup some more
x86/setup/crash: Remove alignment variable
x86/setup: Cleanup crashkernel reservation functions
x86/amd_nb, EDAC: Rename amd_get_node_id()
x86/setup: Do not reserve crashkernel high memory if low reservation failed
x86/microcode/amd: Do not overwrite final patch levels
x86/microcode/amd: Extract current patch level read to a function
x86/ras/mce_amd_inj: Inject bank 4 errors on the NBC
x86/ras/mce_amd_inj: Trigger deferred and thresholding errors interrupts
...
Linus Torvalds [Wed, 4 Nov 2015 01:38:09 +0000 (17:38 -0800)]
Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull perf updates from Ingo Molnar:
"Kernel side changes:
- Improve accuracy of perf/sched clock on x86. (Adrian Hunter)
- Intel DS and BTS updates. (Alexander Shishkin)
- Intel cstate PMU support. (Kan Liang)
- Add group read support to perf_event_read(). (Peter Zijlstra)
- Branch call hardware sampling support, implemented on x86 and
PowerPC. (Stephane Eranian)
- Event groups transactional interface enhancements. (Sukadev
Bhattiprolu)
- Enable proper x86/intel/uncore PMU support on multi-segment PCI
systems. (Taku Izumi)
- ... misc fixes and cleanups.
The perf tooling team was very busy again with 200+ commits, the full
diff doesn't fit into lkml size limits. Here's an (incomplete) list
of the tooling highlights:
New features:
- Change the default event used in all tools (record/top): use the
most precise "cycles" hw counter available, i.e. when the user
doesn't specify any event, it will try using cycles:ppp, cycles:pp,
etc and fall back transparently until it finds a working counter.
(Arnaldo Carvalho de Melo)
- Integration of perf with eBPF that, given an eBPF .c source file
(or .o file built for the 'bpf' target with clang), will get it
automatically built, validated and loaded into the kernel via the
sys_bpf syscall, which can then be used and seen using 'perf trace'
and other tools.
(Wang Nan)
Various user interface improvements:
- Automatic pager invocation on long help output. (Namhyung Kim)
- Search for more options when passing args to -h, e.g.: (Arnaldo
Carvalho de Melo)
$ perf report -h interface
Usage: perf report [<options>]
--gtk Use the GTK2 interface
--stdio Use the stdio interface
--tui Use the TUI interface
- Show ordered command line options when -h is used or when an
unknown option is specified. (Arnaldo Carvalho de Melo)
- If options are passed after -h, show just its descriptions, not all
options. (Arnaldo Carvalho de Melo)
- Implement column based horizontal scrolling in the hists browser
(top, report), making it possible to use the TUI for things like
'perf mem report' where there are many more columns than can fit in
a terminal. (Arnaldo Carvalho de Melo)
- Enhance the error reporting of tracepoint event parsing, e.g.:
$ oldperf record -e sched:sched_switc usleep 1
event syntax error: 'sched:sched_switc'
\___ unknown tracepoint
Run 'perf list' for a list of valid events
Now we get the much nicer:
$ perf record -e sched:sched_switc ls
event syntax error: 'sched:sched_switc'
\___ can't access trace events
Error: No permissions to read /sys/kernel/debug/tracing/events/sched/sched_switc
Hint: Try 'sudo mount -o remount,mode=755 /sys/kernel/debug'
And after we have those mount point permissions fixed:
$ perf record -e sched:sched_switc ls
event syntax error: 'sched:sched_switc'
\___ unknown tracepoint
Error: File /sys/kernel/debug/tracing/events/sched/sched_switc not found.
Hint: Perhaps this kernel misses some CONFIG_ setting to enable this feature?.
I.e. basically now the event parsing routing uses the strerror_open()
routines introduced by and used in 'perf trace' work. (Jiri Olsa)
- Fail properly when pattern matching fails to find a tracepoint,
i.e. '-e non:existent' was being correctly handled, with a proper
error message about that not being a valid event, but '-e
non:existent*' wasn't, fix it. (Jiri Olsa)
- Do event name substring search as last resort in 'perf list'.
(Arnaldo Carvalho de Melo)
- Accept a zero --itrace period, meaning "as often as possible". In
the case of Intel PT that is the same as a period of 1 and a unit
of 'instructions' (i.e. --itrace=i1i). (Adrian Hunter)
- Harmonize itrace's synthesized callchains with the existing
--max-stack tool option. (Adrian Hunter)
- Allow time to be displayed in nanoseconds in 'perf script'.
(Adrian Hunter)
- Warn when AUX data has been lost, just like when processing
PERF_RECORD_LOST. (Adrian Hunter)
- Further document export-to-postgresql.py script. (Adrian Hunter)
- Add option to synthesize branch stack from auxtrace data. (Adrian
Hunter)
Misc notable changes:
- Switch the default callchain output mode to 'graph,0.5,caller', to
make it look like the default for other tools, reducing the
learning curve for people used to 'caller' based viewing. (Arnaldo
Carvalho de Melo)
- various call chain usability enhancements. (Namhyung Kim)
- Introduce the 'P' event modifier, meaning 'max precision level,
please', i.e.:
$ perf record -e cycles:P usleep 1
Is now similar to:
$ perf record usleep 1
Useful, for instance, when specifying multiple events. (Jiri Olsa)
- Add 'socket' sort entry, to sort by the processor socket in 'perf
top' and 'perf report'. (Kan Liang)
- Introduce --socket-filter to 'perf report', for filtering by
processor socket. (Kan Liang)
- Add new "Zoom into Processor Socket" operation in the perf hists
browser, used in 'perf top' and 'perf report'. (Kan Liang)
- Allow probing on kmodules without DWARF. (Masami Hiramatsu)
- Fix 'perf probe -l' for probes added to kernel module functions.
(Masami Hiramatsu)
- Preparatory work for the 'perf stat record' feature that will allow
generating perf.data files with counting data in addition to the
sampling mode we have now (Jiri Olsa)
- ... plus lots of other enhancements that I failed to list properly,
by: Adrian Hunter, Alexander Shishkin, Andi Kleen, Andrzej Hajda,
Arnaldo Carvalho de Melo, Dima Kogan, Don Zickus, Geliang Tang, He
Kuang, Huaitong Han, Ingo Molnar, Jan Stancek, Jiri Olsa, Kan
Liang, Kirill Tkhai, Masami Hiramatsu, Matt Fleming, Namhyung Kim,
Paolo Bonzini, Peter Zijlstra, Rabin Vincent, Scott Wood, Stephane
Eranian, Sukadev Bhattiprolu, Taku Izumi, Vaishali Thakkar, Wang
Nan, Yang Shi and Yunlong Song"
* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (260 commits)
perf unwind: Pass symbol source to libunwind
tools build: Fix libiberty feature detection
perf tools: Compile scriptlets to BPF objects when passing '.c' to --event
perf record: Add clang options for compiling BPF scripts
perf bpf: Attach eBPF filter to perf event
perf tools: Make sure fixdep is built before libbpf
perf script: Enable printing of branch stack
perf trace: Add cmd string table to decode sys_bpf first arg
perf bpf: Collect perf_evsel in BPF object files
perf tools: Load eBPF object into kernel
perf tools: Create probe points for BPF programs
perf tools: Enable passing bpf object file to --event
perf ebpf: Add the libbpf glue
perf tools: Make perf depend on libbpf
perf symbols: Fix endless loop in dso__split_kallsyms_for_kcore
perf tools: Enable pre-event inherit setting by config terms
perf symbols: we can now read separate debug-info files based on a build ID
perf symbols: Fix type error when reading a build-id
perf tools: Search for more options when passing args to -h
perf stat: Cache aggregated map entries in extra cpumap
...
Linus Torvalds [Wed, 4 Nov 2015 01:22:17 +0000 (17:22 -0800)]
atomic: remove all traces of READ_ONCE_CTRL() and atomic*_read_ctrl()
This seems to be a mis-reading of how alpha memory ordering works, and
is not backed up by the alpha architecture manual. The helper functions
don't do anything special on any other architectures, and the arguments
that support them being safe on other architectures also argue that they
are safe on alpha.
Basically, the "control dependency" is between a previous read and a
subsequent write that is dependent on the value read. Even if the
subsequent write is actually done speculatively, there is no way that
such a speculative write could be made visible to other cpu's until it
has been committed, which requires validating the speculation.
Note that most weakely ordered architectures (very much including alpha)
do not guarantee any ordering relationship between two loads that depend
on each other on a control dependency:
read A
if (val == 1)
read B
because the conditional may be predicted, and the "read B" may be
speculatively moved up to before reading the value A. So we require the
user to insert a smp_rmb() between the two accesses to be correct:
read A;
if (A == 1)
smp_rmb()
read B
Alpha is further special in that it can break that ordering even if the
*address* of B depends on the read of A, because the cacheline that is
read later may be stale unless you have a memory barrier in between the
pointer read and the read of the value behind a pointer:
read ptr
read offset(ptr)
whereas all other weakly ordered architectures guarantee that the data
dependency (as opposed to just a control dependency) will order the two
accesses. As a result, alpha needs a "smp_read_barrier_depends()" in
between those two reads for them to be ordered.
The coontrol dependency that "READ_ONCE_CTRL()" and "atomic_read_ctrl()"
had was a control dependency to a subsequent *write*, however, and
nobody can finalize such a subsequent write without having actually done
the read. And were you to write such a value to a "stale" cacheline
(the way the unordered reads came to be), that would seem to lose the
write entirely.
So the things that make alpha able to re-order reads even more
aggressively than other weak architectures do not seem to be relevant
for a subsequent write. Alpha memory ordering may be strange, but
there's no real indication that it is *that* strange.
Also, the alpha architecture reference manual very explicitly talks
about the definition of "Dependence Constraints" in section 5.6.1.7,
where a preceding read dominates a subsequent write.
Such a dependence constraint admittedly does not impose a BEFORE (alpha
architecture term for globally visible ordering), but it does guarantee
that there can be no "causal loop". I don't see how you could avoid
such a loop if another cpu could see the stored value and then impact
the value of the first read. Put another way: the read and the write
could not be seen as being out of order wrt other cpus.
So I do not see how these "x_ctrl()" functions can currently be necessary.
I may have to eat my words at some point, but in the absense of clear
proof that alpha actually needs this, or indeed even an explanation of
how alpha could _possibly_ need it, I do not believe these functions are
called for.
And if it turns out that alpha really _does_ need a barrier for this
case, that barrier still should not be "smp_read_barrier_depends()".
We'd have to make up some new speciality barrier just for alpha, along
with the documentation for why it really is necessary.
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul E McKenney <paulmck@us.ibm.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Ingo Molnar <mingo@kernel.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Linus Torvalds [Wed, 4 Nov 2015 00:10:43 +0000 (16:10 -0800)]
Merge branch 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull locking changes from Ingo Molnar:
"The main changes in this cycle were:
- More gradual enhancements to atomic ops: new atomic*_read_ctrl()
ops, synchronize atomic_{read,set}() ordering requirements between
architectures, add atomic_long_t bitops. (Peter Zijlstra)
- Add _{relaxed|acquire|release}() variants for inc/dec atomics and
use them in various locking primitives: mutex, rtmutex, mcs, rwsem.
This enables weakly ordered architectures (such as arm64) to make
use of more locking related optimizations. (Davidlohr Bueso)
- Implement atomic[64]_{inc,dec}_relaxed() on ARM. (Will Deacon)
- Futex kernel data cache footprint micro-optimization. (Rasmus
Villemoes)
* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
ARM, locking/atomics: Implement _relaxed variants of atomic[64]_{inc,dec}
locking/rwsem: Use acquire/release semantics
locking/mcs: Use acquire/release semantics
locking/rtmutex: Use acquire/release semantics
locking/mutex: Use acquire/release semantics
locking/asm-generic: Add _{relaxed|acquire|release}() variants for inc/dec atomics
atomic: Implement atomic_read_ctrl()
atomic, arch: Audit atomic_{read,set}()
atomic: Add atomic_long_t bitops
futex: Force hot variables into a single cache line
locking/pvqspinlock: Kick the PV CPU unconditionally when _Q_SLOW_VAL
locking/osq: Relax atomic semantics
locking/qrwlock: Rename ->lock to ->wait_lock
locking/Documentation/lockstat: Fix typo - lokcing -> locking
locking/atomics, cmpxchg: Privatize the inclusion of asm/cmpxchg.h
Linus Torvalds [Tue, 3 Nov 2015 23:40:38 +0000 (15:40 -0800)]
Merge branch 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull RCU changes from Ingo Molnar:
"The main changes in this cycle were:
- Improvements to expedited grace periods (Paul E McKenney)
- Performance improvements to and locktorture tests for percpu-rwsem
(Oleg Nesterov, Paul E McKenney)
- Torture-test changes (Paul E McKenney, Davidlohr Bueso)
- Documentation updates (Paul E McKenney)
- Miscellaneous fixes (Paul E McKenney, Boqun Feng, Oleg Nesterov,
Patrick Marlier)"
* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (54 commits)
fs/writeback, rcu: Don't use list_entry_rcu() for pointer offsetting in bdi_split_work_to_wbs()
rcu: Better hotplug handling for synchronize_sched_expedited()
rcu: Enable stall warnings for synchronize_rcu_expedited()
rcu: Add tasks to expedited stall-warning messages
rcu: Add online/offline info to expedited stall warning message
rcu: Consolidate expedited CPU selection
rcu: Prepare for consolidating expedited CPU selection
cpu: Remove try_get_online_cpus()
rcu: Stop excluding CPU hotplug in synchronize_sched_expedited()
rcu: Stop silencing lockdep false positive for expedited grace periods
rcu: Switch synchronize_sched_expedited() to IPI
locktorture: Fix module unwind when bad torture_type specified
torture: Forgive non-plural arguments
rcutorture: Fix unused-function warning for torturing_tasks()
rcutorture: Fix module unwind when bad torture_type specified
rcu_sync: Cleanup the CONFIG_PROVE_RCU checks
locking/percpu-rwsem: Clean up the lockdep annotations in percpu_down_read()
locking/percpu-rwsem: Fix the comments outdated by rcu_sync
locking/percpu-rwsem: Make use of the rcu_sync infrastructure
locking/percpu-rwsem: Make percpu_free_rwsem() after kzalloc() safe
...
Linus Torvalds [Tue, 3 Nov 2015 23:05:52 +0000 (15:05 -0800)]
Merge branch 'core-efi-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull EFI changes from Ingo Molnar:
"The main changes in this cycle were:
- further EFI code generalization to make it more workable for ARM64
- various extensions, such as 64-bit framebuffer address support,
UEFI v2.5 EFI_PROPERTIES_TABLE support
- code modularization simplifications and cleanups
- new debugging parameters
- various fixes and smaller additions"
* 'core-efi-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (23 commits)
efi: Fix warning of int-to-pointer-cast on x86 32-bit builds
efi: Use correct type for struct efi_memory_map::phys_map
x86/efi: Fix kernel panic when CONFIG_DEBUG_VIRTUAL is enabled
efi: Add "efi_fake_mem" boot option
x86/efi: Rename print_efi_memmap() to efi_print_memmap()
efi: Auto-load the efi-pstore module
efi: Introduce EFI_NX_PE_DATA bit and set it from properties table
efi: Add support for UEFIv2.5 Properties table
efi: Add EFI_MEMORY_MORE_RELIABLE support to efi_md_typeattr_format()
efifb: Add support for 64-bit frame buffer addresses
efi/arm64: Clean up efi_get_fdt_params() interface
arm64: Use core efi=debug instead of uefi_debug command line parameter
efi/x86: Move efi=debug option parsing to core
drivers/firmware: Make efi/esrt.c driver explicitly non-modular
efi: Use the generic efi.memmap instead of 'memmap'
acpi/apei: Use appropriate pgprot_t to map GHES memory
arm64, acpi/apei: Implement arch_apei_get_mem_attributes()
arm64/mm: Add PROT_DEVICE_nGnRnE and PROT_NORMAL_WT
acpi, x86: Implement arch_apei_get_mem_attributes()
efi, x86: Rearrange efi_mem_attributes()
...
Linus Torvalds [Tue, 3 Nov 2015 23:04:04 +0000 (15:04 -0800)]
Merge branch 'core-debug-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull wchan kernel address hiding from Ingo Molnar:
"This fixes a wchan related information leak in /proc/PID/stat.
There's a bit of an ABI twist to it: instead of setting the wchan
field to 0 (which is our usual technique) we set it conditionally to a
0/1 flag to keep ABI compatibility with older procps versions that
only fetches /proc/PID/wchan (symbolic names) if the absolute wchan
address is nonzero"
* 'core-debug-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
fs/proc, core/debug: Don't expose absolute kernel addresses via wchan
Linus Torvalds [Tue, 3 Nov 2015 22:40:01 +0000 (14:40 -0800)]
Merge branch 'irq-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull irq updates from Thomas Gleixner:
"The irq departement delivers:
- Rework the irqdomain core infrastructure to accomodate ACPI based
systems. This is required to support ARM64 without creating
artificial device tree nodes.
- Sanitize the ACPI based ARM GIC initialization by making use of the
new firmware independent irqdomain core
- Further improvements to the generic MSI management
- Generalize the irq migration on CPU hotplug
- Improvements to the threaded interrupt infrastructure
- Allow the migration of "chained" low level interrupt handlers
- Allow optional force masking of interrupts in disable_irq[_nosysnc]
- Support for two new interrupt chips - Sigh!
- A larger set of errata fixes for ARM gicv3
- The usual pile of fixes, updates, improvements and cleanups all
over the place"
* 'irq-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (71 commits)
Document that IRQ_NONE should be returned when IRQ not actually handled
PCI/MSI: Allow the MSI domain to be device-specific
PCI: Add per-device MSI domain hook
of/irq: Use the msi-map property to provide device-specific MSI domain
of/irq: Split of_msi_map_rid to reuse msi-map lookup
irqchip/gic-v3-its: Parse new version of msi-parent property
PCI/MSI: Use of_msi_get_domain instead of open-coded "msi-parent" parsing
of/irq: Use of_msi_get_domain instead of open-coded "msi-parent" parsing
of/irq: Add support code for multi-parent version of "msi-parent"
irqchip/gic-v3-its: Add handling of PCI requester id.
PCI/MSI: Add helper function pci_msi_domain_get_msi_rid().
of/irq: Add new function of_msi_map_rid()
Docs: dt: Add PCI MSI map bindings
irqchip/gic-v2m: Add support for multiple MSI frames
irqchip/gic-v3: Fix translation of LPIs after conversion to irq_fwspec
irqchip/mxs: Add Alphascale ASM9260 support
irqchip/mxs: Prepare driver for hardware with different offsets
irqchip/mxs: Panic if ioremap or domain creation fails
irqdomain: Documentation updates
irqdomain/msi: Use fwnode instead of of_node
...
Linus Torvalds [Tue, 3 Nov 2015 22:13:41 +0000 (14:13 -0800)]
Merge branch 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull timer updates from Thomas Gleixner:
"The timer departement provides:
- More y2038 work in the area of ntp and pps.
- Optimization of posix cpu timers
- New time related selftests
- Some new clocksource drivers
- The usual pile of fixes, cleanups and improvements"
* 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (25 commits)
timeconst: Update path in comment
timers/x86/hpet: Type adjustments
clocksource/drivers/armada-370-xp: Implement ARM delay timer
clocksource/drivers/tango_xtal: Add new timer for Tango SoCs
clocksource/drivers/imx: Allow timer irq affinity change
clocksource/drivers/exynos_mct: Use container_of() instead of this_cpu_ptr()
clocksource/drivers/h8300_*: Remove unneeded memset()s
clocksource/drivers/sh_cmt: Remove unneeded memset() in sh_cmt_setup()
clocksource/drivers/em_sti: Remove unneeded memset()s
clocksource/drivers/mediatek: Use GPT as sched clock source
clockevents/drivers/mtk: Fix spurious interrupt leading to crash
posix_cpu_timer: Reduce unnecessary sighand lock contention
posix_cpu_timer: Convert cputimer->running to bool
posix_cpu_timer: Check thread timers only when there are active thread timers
posix_cpu_timer: Optimize fastpath_timer_check()
timers, kselftest: Add 'adjtick' test to validate adjtimex() tick adjustments
timers: Use __fls in apply_slack()
clocksource: Remove return statement from void functions
net: sfc: avoid using timespec
ntp/pps: use y2038 safe types in pps_event_time
...
Linus Torvalds [Tue, 3 Nov 2015 21:54:35 +0000 (13:54 -0800)]
Merge branch 'for-linus' of git://ftp.arm.linux.org.uk/~rmk/linux-arm
Pull ARM updates from Russell King:
"In this ARM merge, we remove more lines than we add. Changes include:
- Enable imprecise aborts early, so that bus errors aren't masked
until later in the boot. This has the side effect that boot
loaders which provoke these aborts can cause the kernel to crash
early in boot, so we install a handler to report this event around
the site where these are enabled.
- Remove the buggy but impossible to enable cmpxchg syscall code.
- Add unwinding annotations to some assembly code.
- Add support for atomic half-word exchange for ARMv6k+.
- Reduce ioremap() alignment for SMP/LPAE cases where we don't need
the large alignment.
- Addition of an "optimal" 3G configuration for systems with 1G of
RAM.
- Increase vmalloc space by 128M.
- Constify some SMP operations structures, which have never been
writable.
- Improve ARMs dma_mmap() support for mapping DMA coherent mappings
into userspace.
- Fix to the NMI backtrace code in the IPI case on ARM where the
failing CPU gets stuck for 10s waiting for its own IPI to be
delivered.
- Removal of legacy PM support from the AMBA bus driver.
- Another fix for the previous fix of vdsomunge"
* 'for-linus' of git://ftp.arm.linux.org.uk/~rmk/linux-arm: (23 commits)
ARM: 8449/1: fix bug in vdsomunge swab32 macro
arm: add missing of_node_put
ARM: 8447/1: catch pending imprecise abort on unmask
ARM: 8446/1: amba: Remove unused callbacks for legacy system PM
ARM: 8443/1: Adding support for atomic half word exchange
ARM: clean up TWD after previous patch
ARM: 8441/2: twd: Don't set CLOCK_EVT_FEAT_C3STOP unconditionally
ARM: 8440/1: remove obsolete documentation
ARM: make highpte an expert option
ARM: 8433/1: add a VMSPLIT_3G_OPT config option
ARM: 8439/1: Fix backtrace generation when IPI is masked
ARM: 8428/1: kgdb: Fix registers on sleeping tasks
ARM: 8427/1: dma-mapping: add support for offset parameter in dma_mmap()
ARM: 8426/1: dma-mapping: add missing range check in dma_mmap()
ARM: remove user cmpxchg syscall
ARM: 8438/1: Add unwinding to __clear_user_std()
ARM: 8436/1: hw_breakpoint: remove unnecessary header
ARM: 8434/2: Revert "7655/1: smp_twd: make twd_local_timer_of_register() no-op for nosmp"
ARM: 8432/1: move VMALLOC_END from 0xff000000 to 0xff800000
ARM: 8430/1: use default ioremap alignment for SMP or LPAE
...
projects / linux-beck.git / log